bbchicago-violet-dpo-ep1

developer_uid: BBChicago

submission_id: bbchicago-violet-dpo-ep1_v1

model_name: violet-dpo-ep1

model_group: BBChicago/violet-dpo-ep1

status: torndown

timestamp: 2025-04-23T07:30:16+00:00

num_battles: 6918

num_wins: 3377

celo_rating: 1286.27

family_friendly_score: 0.5436000000000001

family_friendly_standard_error: 0.007044132877792696

submission_type: basic

model_repo: BBChicago/violet-dpo-ep1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6020506815937333, 'latency_mean': 1.6609265959262849, 'latency_p50': 1.6557209491729736, 'latency_p90': 1.8326792955398559}, {'batch_size': 3, 'throughput': 1.0861430698226897, 'latency_mean': 2.7526505625247957, 'latency_p50': 2.7529382705688477, 'latency_p90': 3.09066846370697}, {'batch_size': 5, 'throughput': 1.3171235790686826, 'latency_mean': 3.780558086633682, 'latency_p50': 3.736372709274292, 'latency_p90': 4.226032686233521}, {'batch_size': 6, 'throughput': 1.3781824712640374, 'latency_mean': 4.331949299573898, 'latency_p50': 4.358710408210754, 'latency_p90': 4.853010511398315}, {'batch_size': 8, 'throughput': 1.430904477446562, 'latency_mean': 5.548461133241654, 'latency_p50': 5.569265604019165, 'latency_p90': 6.2536029577255245}, {'batch_size': 10, 'throughput': 1.4680515991066592, 'latency_mean': 6.756352640390396, 'latency_p50': 6.820449352264404, 'latency_p90': 7.547730231285095}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: violet-dpo-ep1

is_internal_developer: False

language_model: BBChicago/violet-dpo-ep1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-04-23

win_ratio: 0.48814686325527606

generation_params: {'temperature': 0.85, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['[/INST]', '<s>', '\n', '</s>', '[INST]', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "<s>[INST]{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n[/INST]</s>', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': '<s>[INST]{user_name}: {message}[/INST]\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name bbchicago-violet-dpo-ep1-v1-mkmlizer
Waiting for job on bbchicago-violet-dpo-ep1-v1-mkmlizer to finish
bbchicago-violet-dpo-ep1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║                                                                     ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║                                                                     ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║                                                                     ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ║                                                                     ║
bbchicago-violet-dpo-ep1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-violet-dpo-ep1-v1-mkmlizer: Downloaded to shared memory in 40.197s
bbchicago-violet-dpo-ep1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuq7pht9r, device:0
bbchicago-violet-dpo-ep1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-violet-dpo-ep1-v1-mkmlizer: quantized model in 39.072s
bbchicago-violet-dpo-ep1-v1-mkmlizer: Processed model BBChicago/violet-dpo-ep1 in 79.269s
bbchicago-violet-dpo-ep1-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-violet-dpo-ep1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-violet-dpo-ep1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-violet-dpo-ep1-v1
bbchicago-violet-dpo-ep1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-violet-dpo-ep1-v1/config.json
bbchicago-violet-dpo-ep1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-violet-dpo-ep1-v1/special_tokens_map.json
bbchicago-violet-dpo-ep1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-violet-dpo-ep1-v1/tokenizer_config.json
bbchicago-violet-dpo-ep1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-violet-dpo-ep1-v1/tokenizer.json
bbchicago-violet-dpo-ep1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-violet-dpo-ep1-v1/flywheel_model.0.safetensors
bbchicago-violet-dpo-ep1-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.37it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 43.52it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 41.17it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 41.61it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 43.23it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.45it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 42.84it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 42.52it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 42.55it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 43.95it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 44.49it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 24.95it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 32.60it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.64it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:08, 34.66it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 35.99it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:09, 28.91it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:08, 32.90it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:08, 29.99it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:07, 34.06it/s]
Loading 0:  30%|███       | 110/363 [00:03<00:07, 36.09it/s]
Loading 0:  31%|███▏      | 114/363 [00:03<00:07, 33.97it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 31.42it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 39.34it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 38.18it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:06, 37.47it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 37.54it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:08, 24.56it/s]
Loading 0:  40%|████      | 147/363 [00:04<00:08, 26.18it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:07, 26.97it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:07, 29.67it/s]
Loading 0:  44%|████▍     | 159/363 [00:04<00:07, 28.68it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:06, 31.04it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:06, 29.31it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 36.41it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 34.32it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 35.24it/s]
Loading 0:  51%|█████     | 186/363 [00:05<00:05, 30.95it/s]
Loading 0:  52%|█████▏    | 190/363 [00:05<00:05, 32.27it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:05, 29.42it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:04, 33.47it/s]
Loading 0:  56%|█████▌    | 203/363 [00:06<00:05, 31.09it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 34.33it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 31.60it/s]
Loading 0:  60%|█████▉    | 217/363 [00:06<00:04, 35.80it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:03, 36.99it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 23.64it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 24.02it/s]
Loading 0:  65%|██████▍   | 235/363 [00:07<00:04, 28.99it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:04, 27.64it/s]
Loading 0:  68%|██████▊   | 246/363 [00:07<00:03, 34.83it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 33.10it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:03, 35.38it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:03, 34.11it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 35.94it/s]
Loading 0:  74%|███████▍  | 268/363 [00:08<00:02, 34.18it/s]
Loading 0:  75%|███████▌  | 273/363 [00:08<00:02, 36.35it/s]
Loading 0:  76%|███████▋  | 277/363 [00:08<00:02, 34.67it/s]
Loading 0:  78%|███████▊  | 282/363 [00:08<00:02, 35.54it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 34.46it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 37.02it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 34.98it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 33.17it/s]
Loading 0:  83%|████████▎ | 303/363 [00:09<00:01, 34.54it/s]
Loading 0:  85%|████████▍ | 307/363 [00:16<00:29,  1.88it/s]
Loading 0:  86%|████████▌ | 312/363 [00:16<00:18,  2.77it/s]
Loading 0:  88%|████████▊ | 319/363 [00:16<00:09,  4.51it/s]
Loading 0:  89%|████████▉ | 323/363 [00:16<00:06,  5.73it/s]
Loading 0:  90%|█████████ | 328/363 [00:16<00:04,  7.79it/s]
Loading 0:  91%|█████████▏| 332/363 [00:16<00:03,  9.68it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:02, 12.81it/s]
Loading 0:  94%|█████████▍| 341/363 [00:17<00:01, 15.20it/s]
Loading 0:  95%|█████████▌| 346/363 [00:17<00:00, 19.25it/s]
Loading 0:  96%|█████████▋| 350/363 [00:17<00:00, 21.39it/s]
Loading 0:  98%|█████████▊| 354/363 [00:17<00:00, 24.39it/s]
Loading 0:  99%|█████████▊| 358/363 [00:17<00:00, 25.20it/s]
                                                            
Job bbchicago-violet-dpo-ep1-v1-mkmlizer completed after 104.34s with status: succeeded
Stopping job with name bbchicago-violet-dpo-ep1-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.82s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service bbchicago-violet-dpo-ep1-v1
Waiting for inference service bbchicago-violet-dpo-ep1-v1 to be ready
Failed to get response for submission chaiml-nis-cogito32b-si_49363_v1: HTTPConnectionPool(host='chaiml-nis-cogito32b-si-49363-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service bbchicago-violet-dpo-ep1-v1 ready after 120.58057737350464s
Pipeline stage MKMLDeployer completed in 121.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.340162515640259s
Received healthy response to inference request in 1.8018405437469482s
Received healthy response to inference request in 1.7831215858459473s
Received healthy response to inference request in 1.967308521270752s
Received healthy response to inference request in 1.540968656539917s
5 requests
0 failed requests
5th percentile: 1.589399242401123
10th percentile: 1.6378298282623291
20th percentile: 1.7346909999847413
30th percentile: 1.7868653774261474
40th percentile: 1.7943529605865478
50th percentile: 1.8018405437469482
60th percentile: 1.8680277347564698
70th percentile: 1.934214925765991
80th percentile: 2.0418793201446532
90th percentile: 2.1910209178924562
95th percentile: 2.2655917167663575
99th percentile: 2.3252483558654786
mean time: 1.8866803646087646
Pipeline stage StressChecker completed in 10.73s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.67s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.67s
Shutdown handler de-registered
bbchicago-violet-dpo-ep1_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service bbchicago-violet-dpo-ep1-v1-profiler
Waiting for inference service bbchicago-violet-dpo-ep1-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4729.22s
Shutdown handler de-registered
bbchicago-violet-dpo-ep1_v1 status is now inactive due to auto deactivation removed underperforming models
bbchicago-violet-dpo-ep1_v1 status is now torndown due to DeploymentManager action